forked from OSchip/llvm-project
132 lines
3.9 KiB
LLVM
132 lines
3.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=x86-64 -mattr=+avx2 < %s | FileCheck %s --check-prefix=AVX2
|
|
; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=x86-64 -mattr=+avx512f,+avx512vl,+avx512bw < %s | FileCheck %s --check-prefix=AVX512
|
|
|
|
define i16 @v16i16(<16 x i16> %a, <16 x i16> %b) {
|
|
; AVX2-LABEL: v16i16:
|
|
; AVX2: ## BB#0:
|
|
; AVX2-NEXT: vpcmpgtw %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpmovmskb %xmm0, %eax
|
|
; AVX2-NEXT: ## kill: %AX<def> %AX<kill> %EAX<kill>
|
|
; AVX2-NEXT: vzeroupper
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v16i16:
|
|
; AVX512: ## BB#0:
|
|
; AVX512-NEXT: vpcmpgtw %ymm1, %ymm0, %k0
|
|
; AVX512-NEXT: kmovd %k0, %eax
|
|
; AVX512-NEXT: ## kill: %AX<def> %AX<kill> %EAX<kill>
|
|
; AVX512-NEXT: vzeroupper
|
|
; AVX512-NEXT: retq
|
|
%x = icmp sgt <16 x i16> %a, %b
|
|
%res = bitcast <16 x i1> %x to i16
|
|
ret i16 %res
|
|
}
|
|
|
|
define i8 @v8i32(<8 x i32> %a, <8 x i32> %b) {
|
|
; AVX2-LABEL: v8i32:
|
|
; AVX2: ## BB#0:
|
|
; AVX2-NEXT: vpcmpgtd %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vmovmskps %ymm0, %eax
|
|
; AVX2-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; AVX2-NEXT: vzeroupper
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v8i32:
|
|
; AVX512: ## BB#0:
|
|
; AVX512-NEXT: vpcmpgtd %ymm1, %ymm0, %k0
|
|
; AVX512-NEXT: kmovd %k0, %eax
|
|
; AVX512-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; AVX512-NEXT: vzeroupper
|
|
; AVX512-NEXT: retq
|
|
%x = icmp sgt <8 x i32> %a, %b
|
|
%res = bitcast <8 x i1> %x to i8
|
|
ret i8 %res
|
|
}
|
|
|
|
define i8 @v8f32(<8 x float> %a, <8 x float> %b) {
|
|
; AVX2-LABEL: v8f32:
|
|
; AVX2: ## BB#0:
|
|
; AVX2-NEXT: vcmpltps %ymm0, %ymm1, %ymm0
|
|
; AVX2-NEXT: vmovmskps %ymm0, %eax
|
|
; AVX2-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; AVX2-NEXT: vzeroupper
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v8f32:
|
|
; AVX512: ## BB#0:
|
|
; AVX512-NEXT: vcmpltps %ymm0, %ymm1, %k0
|
|
; AVX512-NEXT: kmovd %k0, %eax
|
|
; AVX512-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; AVX512-NEXT: vzeroupper
|
|
; AVX512-NEXT: retq
|
|
%x = fcmp ogt <8 x float> %a, %b
|
|
%res = bitcast <8 x i1> %x to i8
|
|
ret i8 %res
|
|
}
|
|
|
|
define i32 @v32i8(<32 x i8> %a, <32 x i8> %b) {
|
|
; AVX2-LABEL: v32i8:
|
|
; AVX2: ## BB#0:
|
|
; AVX2-NEXT: vpcmpgtb %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpmovmskb %ymm0, %eax
|
|
; AVX2-NEXT: vzeroupper
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v32i8:
|
|
; AVX512: ## BB#0:
|
|
; AVX512-NEXT: vpcmpgtb %ymm1, %ymm0, %k0
|
|
; AVX512-NEXT: kmovd %k0, %eax
|
|
; AVX512-NEXT: vzeroupper
|
|
; AVX512-NEXT: retq
|
|
%x = icmp sgt <32 x i8> %a, %b
|
|
%res = bitcast <32 x i1> %x to i32
|
|
ret i32 %res
|
|
}
|
|
|
|
define i4 @v4i64(<4 x i64> %a, <4 x i64> %b) {
|
|
; AVX2-LABEL: v4i64:
|
|
; AVX2: ## BB#0:
|
|
; AVX2-NEXT: vpcmpgtq %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vmovmskpd %ymm0, %eax
|
|
; AVX2-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; AVX2-NEXT: vzeroupper
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v4i64:
|
|
; AVX512: ## BB#0:
|
|
; AVX512-NEXT: vpcmpgtq %ymm1, %ymm0, %k0
|
|
; AVX512-NEXT: kmovd %k0, %eax
|
|
; AVX512-NEXT: movb %al, -{{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movb -{{[0-9]+}}(%rsp), %al
|
|
; AVX512-NEXT: vzeroupper
|
|
; AVX512-NEXT: retq
|
|
%x = icmp sgt <4 x i64> %a, %b
|
|
%res = bitcast <4 x i1> %x to i4
|
|
ret i4 %res
|
|
}
|
|
|
|
define i4 @v4f64(<4 x double> %a, <4 x double> %b) {
|
|
; AVX2-LABEL: v4f64:
|
|
; AVX2: ## BB#0:
|
|
; AVX2-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0
|
|
; AVX2-NEXT: vmovmskpd %ymm0, %eax
|
|
; AVX2-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; AVX2-NEXT: vzeroupper
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v4f64:
|
|
; AVX512: ## BB#0:
|
|
; AVX512-NEXT: vcmpltpd %ymm0, %ymm1, %k0
|
|
; AVX512-NEXT: kmovd %k0, %eax
|
|
; AVX512-NEXT: movb %al, -{{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movb -{{[0-9]+}}(%rsp), %al
|
|
; AVX512-NEXT: vzeroupper
|
|
; AVX512-NEXT: retq
|
|
%x = fcmp ogt <4 x double> %a, %b
|
|
%res = bitcast <4 x i1> %x to i4
|
|
ret i4 %res
|
|
}
|